This skill package provides text-to-speech functionality based on the Tencent Cloud Text-to-Speech service, focusing on basic single synthesis needs.
Features
- Text-to-Speech: Convert any text content into high-quality speech files
- Multi-format Support: Supports common audio formats such as MP3 and WAV
- Speech Parameter Configuration: Configurable parameters such as voice type and audio format
- Secure Authentication: Securely manage Tencent Cloud API keys through environment variables
Prerequisites
Before using this skill, please ensure:
- Tencent Cloud Account: Have a valid Tencent Cloud account
- API Key: Obtain the SecretId and SecretKey for the Tencent Cloud API
- Service Activation: The Tencent Cloud Text-to-Speech (TTS) service has been activated
Configuration Instructions
Environment Variable Configuration
Configure the Tencent Cloud API key as an environment variable:
export TENCENTCLOUD_SECRET_ID="your-secret-id"
export TENCENTCLOUD_SECRET_KEY="your-secret-key"
Skill Parameter Description
| Parameter Name | Type | Required | Default Value | Description |
|---|---|---|---|---|
| text | string | Yes | - | The text content to be converted into speech |
| voice_type | int | No | 101001 | Voice type (101001-101015) |
| codec | string | No | mp3 | Audio encoding format (mp3/wav) |
| output_file | string | No | output.mp3 | Output audio file name |
Usage Examples
Basic Usage
# 使用默认参数合成语音
from tencent_tts import TextToSpeech
tts = TextToSpeech()
result = tts.synthesize("欢迎使用腾讯云语音合成服务")
print(f"音频文件已生成: {result['output_file']}")
Custom Parameters
# 使用自定义参数
from tencent_tts import TextToSpeech
tts = TextToSpeech()
result = tts.synthesize(
text="这是一个自定义语音合成的示例",
voice_type=101002,
codec="wav",
output_file="custom_voice.wav"
)
print(f"音频文件已生成: {result['output_file']}")
File Structure
tencent-tts/
├── SKILL.md (本文件)
├── scripts/
│ └── tencent_tts.py (主功能脚本)
└── examples/
└── basic_usage.py (基础使用示例)
Best Practices
- Key Security: Do not hard-code API keys in code
- Text Length: It is recommended that a single synthesis text does not exceed 300 characters
- Frequency Control: Avoid high-frequency calls and comply with service limits
- File Management: Regularly clean up generated audio files
Technical Support
If you encounter problems, please refer to:
- Tencent Cloud Text-to-Speech documentation:https://cloud.tencent.com/document/product/1073
- API error code description:https://cloud.tencent.com/document/api/1073/37996